Text Generation
Transformers
PyTorch
English
mistral
text-generation-inference
Inference Endpoints
BSL-470M / config.json
t1101675's picture
Upload MistralForCausalLM
02077f9 verified
raw
history blame contribute delete
736 Bytes
{
"_name_or_path": "results/pretrain/470M_bsl",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_model_parallel": false,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.46.0.dev0",
"use_cache": true,
"use_memory_efficient_attention": true,
"vocab_size": 32000
}